Clustering as an Approach to 3D Reconstruction Problem

Sergey Arkhangelskiy () and Ilya Muchnik ()
Additional contact information
Ilya Muchnik: DIMACS, Rutgers University

A chapter in Clusters, Orders, and Trees: Methods and Applications, 2014, pp 91-102 from Springer

Abstract: Abstract Numerous applications of information technology are connected with 3D-reconstruction task. One of the important special cases is reconstruction using 3D point clouds that are collected by laser range finders and consumer devices like Microsoft Kinect. We present a novel procedure for 3D image registration that is a fundamental step in 3D objects reconstruction. This procedure reduces the task complexity by extracting small subset of potential matches which is enough for accurate registration. We obtain this subset as a result of clustering procedure applied to the broad set of potential matches, where the distance between matches reflects their consistency. Furthermore, we demonstrate the effectiveness of the proposed approach by a set of experiments in comparison with state-of-the-art techniques.

Keywords: 3D object reconstruction; Cluster analysis applications; Point set registration (search for similar items in EconPapers)
Date: 2014
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:spochp:978-1-4939-0742-7_6

Ordering information: This item can be ordered from
http://www.springer.com/9781493907427

DOI: 10.1007/978-1-4939-0742-7_6

Access Statistics for this chapter

More chapters in Springer Optimization and Its Applications from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().